Comparison of PSO-based U-Net and SegNet for Automatic Fundus Image Segmentation
Keywords:
Blood vessel, Fundus, Particle-swarm optimization, SegmentationAbstract
The retinal vascularization morphology can be an important cue for various eye pathologies. Past studies have focused on exploring complex image processing and enhancement methods to improve vessel segmentation and detection for screening eye diseases. This research explores the potential of the Particle Swarm Optimization (PSO) method for optimizing segmentation of vessel images without requiring expensive data or computing resources. This optimization framework searches for important hyperparameters for the efficient training of deep-convolutional U-Net and SegNet on a small fundus dataset. The comparison results showed that U-Net achieves better segmentation of fundus photographs with mean overlap measures of 0.74-0.83 than its competing model. A comparison with the state-of-the-art methods showed considerably high classification accuracy and sensitivity scores ranging from 0.93-0.98 were achieved by the proposed networks. This study identified the insufficiency of the employed data augmentation strategies as the main factor responsible for the poor segmentation sensitivity of 0.52-0.63. Future works include optimizing network parameters and adopting effective image preprocessing processes to improve the detection results.
Downloads
References
J. Yang and M. Li, “Epidemiology of Noncommunicable Diseases,” In: Wang, C., Liu, F. Textbook of Clinical Epidemiology. 1st ed. Singapore: Springer, 2023.
W.S. Wright, R.S. Eshaq, M. Lee, G. Kaur, and N.R. Harris, “Retinal Physiology and Circulation: Effect of Diabetes,” Compr. Physiol., vol.10, pp. 933-974, 2020.
T.H. Rim, A.W.J. Teo, H.H.S. Yang, C.Y. Cheung, and T.Y. Wong, “Retinal Vascular Signs and Cerebrovascular Diseases,” J. Neuro-Ophthalmol., vol.40, pp. 44-59, 2020.
L.K. Singh, M. Khanna, S. Thawkar, and R. Singh, “Deep-learning based system for effective and automatic blood vessel segmentation from Retinal fundus images,” Multimed Tools Appl., vol. 83, pp. 6005–6049, 2024.
J.P.O. Li, H. Liu, D.S.J. Ting, S. Jeon, R.V.P. Chan, J.E. Kim JE, et al. “Digital technology, telemedicine and artificial intelligence in ophthalmology: A global perspective,” Prog. Retin. Eye Res., vol. 82, pp. 1-32, 2021.
R.K. Wang and S.L. Jacques, “Innovative Optical Technologies in Ophthalmology and Eye Research,” J. Ocul. Pharmacol. Ther., vol. 31, no. 3, pp. 142-142, 2021.
J.X. Ong and A.A. Fawzi, “Perspectives on diabetic retinopathy from advanced retinal vascular imaging,” Eye (Lond), vol. 36, pp. 319-327, 2022.
F. Girard, C. Kavalec, and F. Cheriet, “Joint segmentation and classification of retinal arteries/veins from fundus images,” Artif. Intell. Med., vol. 94, pp. 96-109, 2019.
A.Z.M.E. Chowdhury, G. Mann, W.H. Morgan, A. Vukmirovic, A. Mehnert, F. Sohel, “MSGANet-RAV: A multiscale guided attention network for artery-vein segmentation and classification from optic disc and retinal images,” J. Optom., vol. 15, pp. 58-69, 2022.
W. Ma, S. Yu, K. Ma, J. Wang, X. Ding, and Y. Zheng, “Multi-task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification,” In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Lecture Notes in Computer Science; Springer, 2019.
J. Morano, A.S. Hervella, J. Novo, and J. Rouco, “Simultaneous segmentation and classification of the retinal arteries and veins from color fundus images,” Artif. Intell. Med., vol. 118, pp. 102116, 2021.
D. Shi, Z. Lin, W. Wang, Z. Tan, X. Shang, X. Zhang X, et al., “A Deep Learning System for Fully Automated Retinal Vessel Measurement in High Throughput Image Analysis,” Front Cardiovasc. Med., vol. 22, pp. 823436, 2022.
Setyanto, T.B. Sasongko, M.A. Fikri, and I.K. Kim, “Near-Edge Computing Aware Object Detection: A Review,” IEEE Access, vol. 12, pp. 2989-3011, 2024.
X. Liu, M. Pedersen, and R. Wang, “Survey of natural image enhancement techniques: Classification, evaluation, challenges, and perspectives,” Digit. Signal Process, vol.127, pp. 1-40, 2022.
Huong, K.G. Tay, K.B. Gan, and X. Ngu, “A hierarchical optimisation framework for pigmented lesion diagnosis,” CAAI Trans. Intell. Technol., vol. 7, pp. 34–45, 2022.
Akay, D. Karaboga, and R. Akay, “A comprehensive survey on optimizing deep learning models by metaheuristics,” Artif. Intell. Rev., vol. 55, pp. 829–894, 2022.
Q. Hu, M.D. Abràmoff, and M.K. Garvin, “Automated separation of binary overlapping trees in low-contrast color retinal images,” Med. Image Comput. Assist. Interv., vol. 16, pp. 436-43, 2013.
Downloads
Published
How to Cite
Issue
Section
License
![Creative Commons License](http://i.creativecommons.org/l/by-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.